Upload FSMTForConditionalGeneration

.gitattributes

@@ -6,3 +6,4 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,5 +1,5 @@
 ---
-language: 
+language:
 - en
 - ru
 tags:

config.json

@@ -1,37 +1,47 @@
 {
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
     "FSMTForConditionalGeneration"
   ],
-  "model_type": "fsmt",
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
   "attention_dropout": 0.1,
+  "bos_token_id": 0,
   "d_model": 1024,
+  "decoder": {
+    "bos_token_id": 2,
+    "model_type": "fsmt_decoder",
+    "vocab_size": 31232
+  },
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
   "dropout": 0.2,
-  "init_std": 0.02,
-  "max_position_embeddings": 1024,
-  "num_hidden_layers": 6,
-  "src_vocab_size": 31640,
-  "tgt_vocab_size": 31232,
-  "langs": [
-    "en",
-    "ru"
-  ],
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 8192,
   "encoder_layerdrop": 0,
   "encoder_layers": 6,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0,
-  "decoder_layers": 6,
-  "bos_token_id": 0,
-  "pad_token_id": 1,
   "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "init_std": 0.02,
   "is_encoder_decoder": true,
+  "langs": [
+    "en",
+    "ru"
+  ],
+  "length_penalty": null,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "fsmt",
+  "num_beams": 5,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
   "scale_embedding": true,
+  "src_vocab_size": 31640,
+  "tgt_vocab_size": 31232,
   "tie_word_embeddings": false,
-  "num_beams": 5,
-  "early_stopping": false,
-  "length_penalty": 1.15
-}
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0.dev0",
+  "use_cache": true
+}

generation_config.json

@@ -8,5 +8,5 @@
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.27.0.dev0"
+  "transformers_version": "4.53.0.dev0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6520cd7bef8837a0fd69c5f1f1a6805ef03d2eec3919370011b4c26244f999af
+size 1172813064